3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_urllib_parse_unquote,
15 compat_xml_parse_error,
33 from .commonprotocols import RtmpIE
34 from .brightcove import (
38 from .nbc import NBCSportsVPlayerIE
39 from .ooyala import OoyalaIE
40 from .rutv import RUTVIE
41 from .tvc import TVCIE
42 from .sportbox import SportBoxEmbedIE
43 from .smotri import SmotriIE
44 from .myvi import MyviIE
45 from .condenast import CondeNastIE
46 from .udn import UDNEmbedIE
47 from .senateisvp import SenateISVPIE
48 from .svt import SVTIE
49 from .pornhub import PornHubIE
50 from .xhamster import XHamsterEmbedIE
51 from .tnaflix import TNAFlixNetworkEmbedIE
52 from .drtuber import DrTuberIE
53 from .redtube import RedTubeIE
54 from .vimeo import VimeoIE
55 from .dailymotion import (
59 from .onionstudios import OnionStudiosIE
60 from .viewlift import ViewLiftEmbedIE
61 from .mtv import MTVServicesEmbeddedIE
62 from .pladform import PladformIE
63 from .videomore import VideomoreIE
64 from .webcaster import WebcasterFeedIE
65 from .googledrive import GoogleDriveIE
66 from .jwplatform import JWPlatformIE
67 from .digiteka import DigitekaIE
68 from .arkena import ArkenaIE
69 from .instagram import InstagramIE
70 from .liveleak import LiveLeakIE
71 from .threeqsdn import ThreeQSDNIE
72 from .theplatform import ThePlatformIE
73 from .vessel import VesselIE
74 from .kaltura import KalturaIE
75 from .eagleplatform import EaglePlatformIE
76 from .facebook import FacebookIE
77 from .soundcloud import SoundcloudIE
78 from .tunein import TuneInBaseIE
79 from .vbox7 import Vbox7IE
80 from .dbtv import DBTVIE
81 from .piksel import PikselIE
82 from .videa import VideaIE
83 from .twentymin import TwentyMinutenIE
84 from .ustream import UstreamIE
85 from .openload import OpenloadIE
86 from .videopress import VideoPressIE
87 from .rutube import RutubeIE
88 from .limelight import LimelightBaseIE
89 from .anvato import AnvatoIE
90 from .washingtonpost import WashingtonPostIE
91 from .wistia import WistiaIE
92 from .mediaset import MediasetIE
95 class GenericIE(InfoExtractor):
96 IE_DESC = 'Generic downloader that works on some sites'
100 # Direct link to a video
102 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
103 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
108 'upload_date': '20100513',
111 # Direct link to media delivered compressed (until Accept-Encoding is *)
113 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
114 'md5': '128c42e68b13950268b648275386fc74',
116 'id': 'FictionJunction-Parallel_Hearts',
118 'title': 'FictionJunction-Parallel_Hearts',
119 'upload_date': '20140522',
121 'expected_warnings': [
122 'URL could be a direct video link, returning it as such.'
124 'skip': 'URL invalid',
126 # Direct download with broken HEAD
128 'url': 'http://ai-radio.org:8000/radio.opus',
135 'skip_download': True, # infinite live stream
137 'expected_warnings': [
138 r'501.*Not Implemented',
142 # Direct link with incorrect MIME type
144 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
145 'md5': '4ccbebe5f36706d85221f204d7eb5913',
147 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
148 'id': '5_Lennart_Poettering_-_Systemd',
150 'title': '5_Lennart_Poettering_-_Systemd',
151 'upload_date': '20141120',
153 'expected_warnings': [
154 'URL could be a direct video link, returning it as such.'
159 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
161 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
162 'title': 'Zero Punctuation',
163 'description': 're:.*groundbreaking video review series.*'
165 'playlist_mincount': 11,
167 # RSS feed with enclosure
169 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
171 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
173 'upload_date': '20150228',
174 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
177 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
179 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
183 'title': 'Automatics, robotics and biocybernetics',
184 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
185 'upload_date': '20130627',
186 'formats': 'mincount:16',
187 'subtitles': 'mincount:1',
190 'force_generic_extractor': True,
191 'skip_download': True,
194 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
196 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
201 'formats': 'mincount:1',
204 'skip_download': True,
207 # SMIL from https://www.restudy.dk/video/play/id/1637
209 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
213 'title': 'video_1637',
214 'formats': 'mincount:3',
217 'skip_download': True,
220 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
222 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
224 'id': 'smil-service',
226 'title': 'smil-service',
227 'formats': 'mincount:1',
230 'skip_download': True,
233 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
235 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
239 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
240 'formats': 'mincount:3',
243 'skip_download': True,
246 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
248 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
250 'id': 'mZlp2ctYIUEB',
252 'title': 'Tikibad ontruimd wegens brand',
253 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
254 'thumbnail': r're:^https?://.*\.jpg$',
258 'skip_download': True,
261 # MPD from http://dash-mse-test.appspot.com/media.html
263 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
264 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
266 'id': 'car-20120827-manifest',
268 'title': 'car-20120827-manifest',
269 'formats': 'mincount:9',
270 'upload_date': '20130904',
273 'format': 'bestvideo',
276 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
278 'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
283 'formats': 'mincount:8',
287 'skip_download': True,
289 'skip': 'video gone',
291 # m3u8 served with Content-Type: text/plain
293 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
298 'upload_date': '20140720',
299 'formats': 'mincount:11',
303 'skip_download': True,
305 'skip': 'video gone',
309 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
313 'upload_date': '20130224',
314 'uploader_id': 'TheVerge',
315 'description': r're:^Chris Ziegler takes a look at the\.*',
316 'uploader': 'The Verge',
317 'title': 'First Firefox OS phones side-by-side',
320 'skip_download': False,
324 # redirect in Refresh HTTP header
325 'url': 'https://www.facebook.com/l.php?u=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DpO8h3EaFRdo&h=TAQHsoToz&enc=AZN16h-b6o4Zq9pZkCCdOLNKMN96BbGMNtcFwHSaazus4JHT_MFYkAA-WARTX2kvsCIdlAIyHZjl6d33ILIJU7Jzwk_K3mcenAXoAzBNoZDI_Q7EXGDJnIhrGkLXo_LJ_pAa2Jzbx17UHMd3jAs--6j2zaeto5w9RTn8T_1kKg3fdC5WPX9Dbb18vzH7YFX0eSJmoa6SP114rvlkw6pkS1-T&s=1',
329 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
330 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
331 'upload_date': '20150917',
332 'uploader_id': 'brtvofficial',
333 'uploader': 'Boiler Room',
336 'skip_download': False,
340 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
341 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
343 'id': '13601338388002',
345 'uploader': 'www.hodiho.fr',
346 'title': 'R\u00e9gis plante sa Jeep',
349 # bandcamp page with custom domain
351 'add_ie': ['Bandcamp'],
352 'url': 'http://bronyrock.com/track/the-pony-mash',
356 'title': 'The Pony Mash',
357 'uploader': 'M_Pallante',
359 'skip': 'There is a limit of 200 free downloads / month for the test song',
362 # embedded brightcove video
363 # it also tests brightcove videos that need to set the 'Referer'
364 # in the http requests
365 'add_ie': ['BrightcoveLegacy'],
366 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
368 'id': '2765128793001',
370 'title': 'Le cours de bourse : l’analyse technique',
371 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
372 'uploader': 'BFM BUSINESS',
375 'skip_download': True,
379 # embedded with itemprop embedURL and video id spelled as `idVideo`
380 'add_id': ['BrightcoveLegacy'],
381 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
383 'id': '5255628253001',
385 'title': 'md5:37c519b1128915607601e75a87995fc0',
386 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
387 'uploader': 'BFM BUSINESS',
388 'uploader_id': '876450612001',
389 'timestamp': 1482255315,
390 'upload_date': '20161220',
393 'skip_download': True,
397 # https://github.com/rg3/youtube-dl/issues/2253
398 'url': 'http://bcove.me/i6nfkrc3',
399 'md5': '0ba9446db037002366bab3b3eb30c88c',
401 'id': '3101154703001',
403 'title': 'Still no power',
404 'uploader': 'thestar.com',
405 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
407 'add_ie': ['BrightcoveLegacy'],
408 'skip': 'video gone',
411 'url': 'http://www.championat.com/video/football/v/87/87499.html',
412 'md5': 'fb973ecf6e4a78a67453647444222983',
414 'id': '3414141473001',
416 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
417 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
418 'uploader': 'Championat',
422 # https://github.com/rg3/youtube-dl/issues/3541
423 'add_ie': ['BrightcoveLegacy'],
424 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
426 'id': '3866516442001',
428 'title': 'Leer mij vrouwen kennen: Aflevering 1',
429 'description': 'Leer mij vrouwen kennen: Aflevering 1',
430 'uploader': 'SBS Broadcasting',
432 'skip': 'Restricted to Netherlands',
434 'skip_download': True, # m3u8 download
438 # Brightcove video in <iframe>
439 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
440 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
442 'id': '5360463607001',
444 'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
445 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼(Zade Dirani)在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》(HEARTBEAT),为受到六年冲突影响的叙利亚儿童发出强烈呐喊,呼吁世界做出共同努力,使叙利亚儿童重新获得享有正常童年生活的权利。',
446 'uploader': 'United Nations',
447 'uploader_id': '1362235914001',
448 'timestamp': 1489593889,
449 'upload_date': '20170315',
451 'add_ie': ['BrightcoveLegacy'],
454 # Brightcove with alternative playerID key
455 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
457 'id': 'nmeth.2062_SV1',
458 'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
462 'id': '2228375078001',
464 'title': 'nmeth.2062-sv1',
465 'description': 'nmeth.2062-sv1',
466 'timestamp': 1363357591,
467 'upload_date': '20130315',
468 'uploader': 'Nature Publishing Group',
469 'uploader_id': '1964492299001',
474 # Brightcove with UUID in videoPlayer
475 'url': 'http://www8.hp.com/cn/zh/home.html',
477 'id': '5255815316001',
479 'title': 'Sprocket Video - China',
480 'description': 'Sprocket Video - China',
481 'uploader': 'HP-Video Gallery',
482 'timestamp': 1482263210,
483 'upload_date': '20161220',
484 'uploader_id': '1107601872001',
487 'skip_download': True, # m3u8 download
489 'skip': 'video rotates...weekly?',
492 # Brightcove:new type [2].
493 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
494 'md5': '2b35148fcf48da41c9fb4591650784f3',
496 'id': '5348741021001',
498 'upload_date': '20170306',
499 'uploader_id': '4191638492001',
500 'timestamp': 1488769918,
501 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
506 # Alternative brightcove <video> attributes
507 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
509 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
510 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
513 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
515 'id': '5311302538001',
517 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
518 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
519 'timestamp': 1486321708,
520 'upload_date': '20170205',
521 'uploader_id': '800000640001',
523 'only_matching': True,
527 # Brightcove with UUID in videoPlayer
528 'url': 'http://www8.hp.com/cn/zh/home.html',
530 'id': '5255815316001',
532 'title': 'Sprocket Video - China',
533 'description': 'Sprocket Video - China',
534 'uploader': 'HP-Video Gallery',
535 'timestamp': 1482263210,
536 'upload_date': '20161220',
537 'uploader_id': '1107601872001',
540 'skip_download': True, # m3u8 download
545 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
546 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
548 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
550 'title': '2cc213299525360.mov', # that's what we get
553 'add_ie': ['Ooyala'],
556 # ooyala video embedded with http://player.ooyala.com/iframe.js
557 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
559 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
561 'title': '"Steve Jobs: Man in the Machine" trailer',
562 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
566 'skip_download': True,
568 'skip': 'movie expired',
572 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
576 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
577 'upload_date': '20140225',
578 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
579 'uploader': 'Tested',
580 'uploader_id': 'testedcom',
582 # No need to test YoutubeIE here
584 'skip_download': True,
589 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
593 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
594 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
596 # HEAD requests lead to endless 301, while GET is OK
597 'expected_warnings': ['301'],
601 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
605 'title': 'Охотское море стало целиком российским',
606 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
610 'skip_download': True,
615 'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
619 'title': 'Дошкольное воспитание',
624 'url': 'http://www.vestifinance.ru/articles/25753',
627 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
632 'title': 'Госзаказ. День 3',
638 'title': 'Госзаказ. День 2',
644 'title': 'Госзаказ. День 1',
650 'skip_download': True,
655 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
657 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
659 'title': 'Ужастики, русский трейлер (2015)',
660 'thumbnail': r're:^https?://.*\.jpg$',
666 'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
669 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
671 'playlist_mincount': 7,
672 # This forum does not allow <iframe> syntaxes anymore
673 # Now HTML tags are displayed as-is
674 'skip': 'No videos on this page',
678 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
679 'md5': '65fdff94098e4a607385a60c5177c638',
683 'title': 'Hidden miracles of the natural world',
684 'uploader': 'Louie Schwartzberg',
685 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
688 # nowvideo embed hidden behind percent encoding
690 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
691 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
693 'id': '06e53103ca9aa',
695 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
696 'description': 'No description',
701 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
702 'md5': '7653032cbb25bf6c80d80f217055fa43',
704 'id': '048195-004_PLUS7-F',
707 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
708 'upload_date': '20140320',
711 'skip_download': 'Requires rtmpdump'
713 'skip': 'video gone',
717 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
721 'title': 'Alcaline, le concert avec Calogero',
722 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
723 'upload_date': '20150226',
724 'timestamp': 1424989860,
729 'skip_download': True,
731 'expected_warnings': [
737 'url': 'http://www.wired.com/2014/04/honda-asimo/',
738 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
740 'id': '53501be369702d3275860000',
742 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
747 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
748 'md5': '441aeeb82eb72c422c7f14ec533999cd',
750 'id': 'k2mm4bCdJ6CQ2i7c8o2',
752 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
753 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
755 'uploader_id': 'xgditw',
756 'upload_date': '20140425',
757 'timestamp': 1398441542,
759 'add_ie': ['Dailymotion'],
763 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
767 'title': 'The NBL Auction 2014',
768 'uploader': 'BADMINTON England',
769 'uploader_id': 'BADMINTONEvents',
770 'upload_date': '20140603',
771 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
773 'add_ie': ['Youtube'],
775 'skip_download': True,
780 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
781 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
783 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
785 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
786 'description': 'Two valets share their love for movie star Liam Neesons.',
787 'timestamp': 1349922600,
788 'upload_date': '20121011',
791 # YouTube embed via <data-embed-url="">
793 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
797 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
798 'uploader': 'Gameloft',
799 'uploader_id': 'gameloft',
800 'upload_date': '20140828',
801 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
804 'skip_download': True,
807 # YouTube <object> embed
809 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
810 'md5': '516718101ec834f74318df76259fb3cc',
814 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
815 'upload_date': '20080526',
816 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
817 'uploader': 'Christopher Sykes',
818 'uploader_id': 'ChristopherJSykes',
820 'add_ie': ['Youtube'],
824 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
826 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
828 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
829 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
834 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
836 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
837 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
843 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
848 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
849 'md5': '9d65602bf31c6e20014319c7d07fba27',
851 'id': '5123ea6d5e5a7',
854 'uploader': 'www.handjobhub.com',
855 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
858 # Multiple brightcove videos
859 # https://github.com/rg3/youtube-dl/issues/2283
861 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
863 'id': 'always-never',
864 'title': 'Always / Never - The New Yorker',
868 'extract_flat': False,
869 'skip_download': True,
874 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
875 'md5': '96f09a37e44da40dd083e12d9a683327',
879 'title': 'Ump changes call to ball',
880 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
882 'timestamp': 1401537900,
883 'upload_date': '20140531',
884 'thumbnail': r're:^https?://.*\.jpg$',
889 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
890 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
894 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
895 'description': 'a Paywall Videos video from Remilon',
897 'uploader': 'study.com',
898 'timestamp': 1459678540,
899 'upload_date': '20160403',
900 'filesize': 24687186,
904 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
905 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
909 'title': 'Conversation about Hexagonal Rails Part 1',
910 'description': 'a Martin Fowler video from ThoughtWorks',
912 'uploader': 'thoughtworks.wistia.com',
913 'timestamp': 1401832161,
914 'upload_date': '20140603',
917 # Wistia standard embed (async)
919 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
923 'title': 'Drip Brennan Dunn Workshop',
924 'description': 'a JV Webinars video from getdrip-1',
926 'timestamp': 1463607249,
927 'upload_date': '20160518',
930 'skip_download': True,
935 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
939 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
940 'uploader': 'Sophos Security',
941 'title': 'Chet Chat 171 - Oct 29, 2014',
942 'upload_date': '20141029',
945 # Soundcloud multiple embeds
947 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
950 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
952 'playlist_mincount': 7,
954 # TuneIn station embed
956 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
961 'location': 'Paris, France',
966 'skip_download': True,
971 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
975 'upload_date': '20141112',
976 'title': 'Rosetta #CometLanding webcast HL 10',
979 # Another Livestream embed, without 'new.' in URL
981 'url': 'https://www.freespeech.org/',
985 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
989 'skip_download': True,
994 'url': 'https://skiplagged.com/',
997 'title': 'Skiplagged: The smart way to find cheap flights',
999 'playlist_mincount': 1,
1000 'add_ie': ['Youtube'],
1004 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1008 'upload_date': '20141126',
1009 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1014 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1016 'id': '730m_DandD_1901_512k',
1018 'uploader': 'www.abc.net.au',
1019 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1022 # embedded viddler video
1024 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1028 'uploader': 'deadspin',
1029 'title': 'WALL-TO-GORTAT',
1030 'timestamp': 1422285291,
1031 'upload_date': '20150126',
1033 'add_ie': ['Viddler'],
1037 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1041 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1042 'description': 'md5:601cb790edd05908957dae8aaa866465',
1043 'upload_date': '20150220',
1045 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1049 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1051 'id': 'Mrj4DVp2zeA',
1053 'upload_date': '20150212',
1054 'uploader': 'The National Archives UK',
1055 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1056 'uploader_id': 'NationalArchives08',
1057 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1062 'url': 'http://www.suffolk.edu/sjc/',
1066 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1067 'uploader': 'www.suffolk.edu',
1070 'skip_download': True,
1075 'url': 'http://www.indiedb.com/games/king-machine/videos',
1079 'title': 'king machine trailer 1',
1080 'thumbnail': r're:^https?://.*\.jpg$',
1084 # JWPlayer config passed as variable
1085 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1089 'title': 'ARIELE | Tube Cup',
1090 'uploader': 'www.txxx.com',
1094 'skip_download': True,
1099 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1100 'playlist_mincount': 5,
1102 'id': 'aanslagen-kopenhagen',
1103 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1108 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1112 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1115 # Kaltura embed (different embed code)
1117 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1121 'upload_date': '20150127',
1122 'uploader_id': 'PremierMedia',
1124 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1127 # Kaltura embed with single quotes
1129 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1134 'timestamp': 1355743100,
1135 'upload_date': '20121217',
1136 'uploader_id': 'batchUser',
1138 'add_ie': ['Kaltura'],
1141 # Kaltura embedded via quoted entry_id
1142 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1146 'title': '06_matthew_brender_raj_dutt',
1147 'timestamp': 1466638791,
1148 'upload_date': '20160622',
1150 'add_ie': ['Kaltura'],
1151 'expected_warnings': [
1152 'Could not send HEAD request'
1155 'skip_download': True,
1159 # Kaltura embedded, some fileExt broken (#11480)
1160 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1164 'title': 'Our "Standard Models" of particle physics and cosmology',
1165 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1166 'timestamp': 1321158993,
1167 'upload_date': '20111113',
1168 'uploader_id': 'kps1',
1170 'add_ie': ['Kaltura'],
1173 # Kaltura iframe embed
1174 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1175 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1179 'title': 'I. M. Pei: A Centennial Celebration',
1180 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1181 'upload_date': '20170403',
1182 'uploader_id': 'batchUser',
1183 'timestamp': 1491232186,
1185 'add_ie': ['Kaltura'],
1187 # Eagle.Platform embed (generic URL)
1189 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1190 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1194 'title': 'Навальный вышел на свободу',
1195 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1196 'thumbnail': r're:^https?://.*\.jpg$',
1202 # ClipYou (Eagle.Platform) embed (custom URL)
1204 'url': 'http://muz-tv.ru/play/7129/',
1205 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1209 'title': "'O Sole Mio",
1210 'thumbnail': r're:^https?://.*\.jpg$',
1217 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1221 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1222 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1223 'thumbnail': r're:^https?://.*\.jpg$',
1230 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1234 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1235 'thumbnail': r're:^https?://.*\.png$',
1241 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1242 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1246 'title': 'Facebook Creates "On This Day" | Crunch Report',
1251 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1255 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1260 # Crooks and Liars embed
1262 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1266 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1267 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1268 'timestamp': 1428207000,
1269 'upload_date': '20150405',
1270 'uploader': 'Heather',
1273 # Crooks and Liars external embed
1275 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1277 'id': 'MTE3MjUtMzQ2MzA',
1279 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1280 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1281 'timestamp': 1265032391,
1282 'upload_date': '20100201',
1283 'uploader': 'Heather',
1286 # NBC Sports vplayer embed
1288 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1290 'id': 'ln7x1qSThw4k',
1292 'title': "PFT Live: New leader in the 'new-look' defense",
1293 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1294 'uploader': 'NBCU-SPORTS',
1295 'upload_date': '20140107',
1296 'timestamp': 1389118457,
1301 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1302 'md5': '1aa589c675898ae6d37a17913cf68d66',
1304 'id': '701714499682',
1306 'title': 'PREVIEW: On Assignment: David Letterman',
1307 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
1312 'url': 'https://video.udn.com/news/300346',
1313 'md5': 'fd2060e988c326991037b9aff9df21a6',
1317 'title': '中一中男師變性 全校師生力挺',
1318 'thumbnail': r're:^https?://.*\.jpg$',
1322 'skip_download': True,
1327 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1329 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1331 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1332 'title': 'This is what separates the Excel masters from the wannabes',
1333 'duration': 191.933,
1337 'skip_download': True,
1340 # Brightcove URL in single quotes
1342 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1343 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1345 'id': '4255764656001',
1347 'title': 'SN Presents: Russell Martin, World Citizen',
1348 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1349 'uploader': 'Rogers Sportsnet',
1350 'uploader_id': '1704050871',
1351 'upload_date': '20150525',
1352 'timestamp': 1432570283,
1355 # Dailymotion Cloud video
1357 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1358 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1362 'title': 'Sauvons les abeilles ! - Le débat',
1363 'description': 'md5:d9082128b1c5277987825d684939ca26',
1364 'thumbnail': r're:^https?://.*\.jpe?g$',
1365 'timestamp': 1434970506,
1366 'upload_date': '20150622',
1367 'uploader': 'Public Sénat',
1368 'uploader_id': 'xa9gza',
1371 # OnionStudios embed
1373 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1377 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1378 'thumbnail': r're:^https?://.*\.jpe?g$',
1379 'uploader': 'ClickHole',
1380 'uploader_id': 'clickhole',
1385 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1387 'id': '74849a00-85a9-11e1-9660-123139220831',
1389 'title': '#whilewewatch',
1392 # AdobeTVVideo embed
1394 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1395 'md5': '43662b577c018ad707a63766462b1e87',
1399 'title': 'New experience with Acrobat DC',
1400 'description': 'New experience with Acrobat DC',
1401 'duration': 248.667,
1404 # BrightcoveInPageEmbed embed
1406 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1408 'id': '4238694884001',
1410 'title': 'Tabletop: Dread, Last Thoughts',
1411 'description': 'Tabletop: Dread, Last Thoughts',
1415 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1416 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1418 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1420 'id': '4785848093001',
1422 'title': 'The Cardinal Pell Interview',
1423 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1424 'uploader': 'GlobeCast Australia - GlobeStream',
1425 'uploader_id': '2733773828001',
1426 'upload_date': '20160304',
1427 'timestamp': 1457083087,
1431 'skip_download': True,
1435 # Brightcove embed with whitespace around attribute names
1436 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1438 'id': '3167554373001',
1440 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1441 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1442 'uploader_id': '1079349493',
1443 'upload_date': '20140207',
1444 'timestamp': 1391810548,
1447 'skip_download': True,
1450 # Another form of arte.tv embed
1452 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1453 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1455 'id': '030273-562_PLUS7-F',
1457 'title': 'ARTE Reportage - Nulle part, en France',
1458 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1459 'upload_date': '20160409',
1464 'url': 'http://www.wykop.pl/link/3088787/',
1465 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1467 'id': '874_1459135191',
1469 'title': 'Man shows poor quality of new apartment building',
1470 'description': 'The wall is like a sand pile.',
1471 'uploader': 'Lake8737',
1474 # Duplicated embedded video URLs
1476 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1478 'id': '149298443_480_16c25b74_2',
1480 'title': 'vs. Blue Orange Spring Game',
1481 'uploader': 'www.hudl.com',
1484 # twitter:player:stream embed
1486 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1490 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1491 'uploader': 'www.rtl.be',
1495 'skip_download': True,
1498 # twitter:player embed
1500 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1501 'md5': 'a3e0df96369831de324f0778e126653c',
1503 'id': '4909620399001',
1505 'title': 'What Do Black Holes Sound Like?',
1506 'description': 'what do black holes sound like',
1507 'upload_date': '20160524',
1508 'uploader_id': '29913724001',
1509 'timestamp': 1464107587,
1510 'uploader': 'TheAtlantic',
1512 'add_ie': ['BrightcoveLegacy'],
1514 # Facebook <iframe> embed
1516 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1517 'md5': 'fbcde74f534176ecb015849146dd3aee',
1519 'id': '599637780109885',
1521 'title': 'Facebook video #599637780109885',
1524 # Facebook API embed
1526 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1527 'md5': 'a47372ee61b39a7b90287094d447d94e',
1529 'id': '10153467542406923',
1531 'title': 'Facebook video #10153467542406923',
1534 # Wordpress "YouTube Video Importer" plugin
1536 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1537 'md5': 'd16797741b560b485194eddda8121b48',
1539 'id': 'HNTXWDXV9Is',
1541 'title': 'Blue Devils Drumline Stanford lot 2016',
1542 'upload_date': '20160627',
1543 'uploader_id': 'GENOCIDE8GENERAL10',
1544 'uploader': 'cylus cyrus',
1548 # video stored on custom kaltura server
1549 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1550 'md5': '537617d06e64dfed891fa1593c4b30cc',
1554 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1555 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1556 'uploader_id': 'videos.expansion@el-mundo.net',
1557 'upload_date': '20150429',
1558 'timestamp': 1430303472,
1560 'add_ie': ['Kaltura'],
1563 # Non-standard Vimeo embed
1564 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1565 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1569 'title': 'Understanding the web - Teaser',
1570 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1571 'upload_date': '20151214',
1572 'uploader': 'OpenClassrooms',
1573 'uploader_id': 'openclassrooms',
1575 'add_ie': ['Vimeo'],
1578 # generic vimeo embed that requires original URL passed as Referer
1579 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1580 'only_matching': True,
1583 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1584 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1586 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1588 'title': 'Big Buck Bunny',
1589 'description': 'Royalty free test video',
1590 'timestamp': 1432816365,
1591 'upload_date': '20150528',
1595 'skip_download': True,
1597 'add_ie': [ArkenaIE.ie_key()],
1600 'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
1604 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1607 'skip_download': True,
1609 'add_ie': [Vbox7IE.ie_key()],
1613 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1616 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1618 'playlist_mincount': 3,
1622 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1624 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1625 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1627 'playlist_mincount': 2,
1631 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1635 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1636 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1639 'skip_download': True,
1641 'add_ie': [TwentyMinutenIE.ie_key()],
1645 'url': 'https://en.support.wordpress.com/videopress/',
1649 'title': 'IMG_5786',
1650 'timestamp': 1435711927,
1651 'upload_date': '20150701',
1654 'skip_download': True,
1656 'add_ie': [VideoPressIE.ie_key()],
1660 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1662 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1664 'title': 'Магаззино: Казань 2',
1665 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1666 'uploader': 'Магаззино',
1667 'upload_date': '20170228',
1668 'uploader_id': '996642',
1671 'skip_download': True,
1673 'add_ie': [RutubeIE.ie_key()],
1676 # ThePlatform embedded with whitespaces in URLs
1677 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1678 'only_matching': True,
1681 # Senate ISVP iframe https
1682 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1683 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1685 'id': 'govtaff020316',
1687 'title': 'Integrated Senate Video Player',
1689 'add_ie': [SenateISVPIE.ie_key()],
1692 # Limelight embeds (1 channel embed + 4 media embeds)
1693 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1695 'id': 'FacilitatorTraining2017',
1696 'title': 'Facilitator Training 2017',
1698 'playlist_mincount': 5,
1701 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1703 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1704 'title': 'Standoff with Walnut Creek murder suspect ends',
1705 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1707 'playlist_mincount': 4,
1710 # WashingtonPost embed
1711 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1713 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1715 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1716 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
1717 'timestamp': 1455216756,
1718 'uploader': 'The Washington Post',
1719 'upload_date': '20160211',
1721 'add_ie': [WashingtonPostIE.ie_key()],
1724 # # TODO: find another test
1725 # # http://schema.org/VideoObject
1726 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1727 # 'md5': '888dcf08b7ea671381f00fab74692755',
1729 # 'id': 'nyvTSJMKId',
1731 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1732 # 'description': '#love for cats.',
1733 # 'timestamp': 1461244995,
1734 # 'upload_date': '20160421',
1737 # 'force_generic_extractor': True,
1742 def report_following_redirect(self, new_url):
1743 """Report information extraction."""
1744 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1746 def _extract_rss(self, url, video_id, doc):
1747 playlist_title = doc.find('./channel/title').text
1748 playlist_desc_el = doc.find('./channel/description')
1749 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1752 for it in doc.findall('./channel/item'):
1753 next_url = xpath_text(it, 'link', fatal=False)
1755 enclosure_nodes = it.findall('./enclosure')
1756 for e in enclosure_nodes:
1757 next_url = e.attrib.get('url')
1765 '_type': 'url_transparent',
1767 'title': it.find('title').text,
1771 '_type': 'playlist',
1773 'title': playlist_title,
1774 'description': playlist_desc,
1778 def _extract_camtasia(self, url, video_id, webpage):
1779 """ Returns None if no camtasia video can be found. """
1781 camtasia_cfg = self._search_regex(
1782 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1783 webpage, 'camtasia configuration file', default=None)
1784 if camtasia_cfg is None:
1787 title = self._html_search_meta('DC.title', webpage, fatal=True)
1789 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1790 camtasia_cfg = self._download_xml(
1791 camtasia_url, video_id,
1792 note='Downloading camtasia configuration',
1793 errnote='Failed to download camtasia configuration')
1794 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1797 for n in fileset_node.getchildren():
1798 url_n = n.find('./uri')
1803 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1804 'title': '%s - %s' % (title, n.tag),
1805 'url': compat_urlparse.urljoin(url, url_n.text),
1806 'duration': float_or_none(n.find('./duration').text),
1810 '_type': 'playlist',
1815 def _real_extract(self, url):
1816 if url.startswith('//'):
1819 'url': self.http_scheme() + url,
1822 parsed_url = compat_urlparse.urlparse(url)
1823 if not parsed_url.scheme:
1824 default_search = self._downloader.params.get('default_search')
1825 if default_search is None:
1826 default_search = 'fixup_error'
1828 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1830 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1831 return self.url_result('http://' + url)
1832 elif default_search != 'fixup_error':
1833 if default_search == 'auto_warning':
1834 if re.match(r'^(?:url|URL)$', url):
1835 raise ExtractorError(
1836 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1839 self._downloader.report_warning(
1840 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1841 return self.url_result('ytsearch:' + url)
1843 if default_search in ('error', 'fixup_error'):
1844 raise ExtractorError(
1845 '%r is not a valid URL. '
1846 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1847 % (url, url), expected=True)
1849 if ':' not in default_search:
1850 default_search += ':'
1851 return self.url_result(default_search + url)
1853 url, smuggled_data = unsmuggle_url(url)
1854 force_videoid = None
1855 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1856 if smuggled_data and 'force_videoid' in smuggled_data:
1857 force_videoid = smuggled_data['force_videoid']
1858 video_id = force_videoid
1860 video_id = self._generic_id(url)
1862 self.to_screen('%s: Requesting header' % video_id)
1864 head_req = HEADRequest(url)
1865 head_response = self._request_webpage(
1867 note=False, errnote='Could not send HEAD request to %s' % url,
1870 if head_response is not False:
1871 # Check for redirect
1872 new_url = head_response.geturl()
1874 self.report_following_redirect(new_url)
1876 new_url = smuggle_url(
1877 new_url, {'force_videoid': force_videoid})
1878 return self.url_result(new_url)
1880 full_response = None
1881 if head_response is False:
1882 request = sanitized_Request(url)
1883 request.add_header('Accept-Encoding', '*')
1884 full_response = self._request_webpage(request, video_id)
1885 head_response = full_response
1889 'title': self._generic_title(url),
1890 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1893 # Check for direct link to a video
1894 content_type = head_response.headers.get('Content-Type', '').lower()
1895 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1897 format_id = m.group('format_id')
1898 if format_id.endswith('mpegurl'):
1899 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1900 elif format_id == 'f4m':
1901 formats = self._extract_f4m_formats(url, video_id)
1904 'format_id': m.group('format_id'),
1906 'vcodec': 'none' if m.group('type') == 'audio' else None
1908 info_dict['direct'] = True
1909 self._sort_formats(formats)
1910 info_dict['formats'] = formats
1913 if not self._downloader.params.get('test', False) and not is_intentional:
1914 force = self._downloader.params.get('force_generic_extractor', False)
1915 self._downloader.report_warning(
1916 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1918 if not full_response:
1919 request = sanitized_Request(url)
1920 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1921 # making it impossible to download only chunk of the file (yet we need only 512kB to
1922 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1923 # that will always result in downloading the whole file that is not desirable.
1924 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1925 # to accept raw bytes and being able to download only a chunk.
1926 # It may probably better to solve this by checking Content-Type for application/octet-stream
1927 # after HEAD request finishes, but not sure if we can rely on this.
1928 request.add_header('Accept-Encoding', '*')
1929 full_response = self._request_webpage(request, video_id)
1931 first_bytes = full_response.read(512)
1933 # Is it an M3U playlist?
1934 if first_bytes.startswith(b'#EXTM3U'):
1935 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1936 self._sort_formats(info_dict['formats'])
1939 # Maybe it's a direct link to a video?
1940 # Be careful not to download the whole thing!
1941 if not is_html(first_bytes):
1942 self._downloader.report_warning(
1943 'URL could be a direct video link, returning it as such.')
1950 webpage = self._webpage_read_content(
1951 full_response, url, video_id, prefix=first_bytes)
1953 self.report_extraction(video_id)
1955 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1957 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1958 if doc.tag == 'rss':
1959 return self._extract_rss(url, video_id, doc)
1960 elif doc.tag == 'SmoothStreamingMedia':
1961 info_dict['formats'] = self._parse_ism_formats(doc, url)
1962 self._sort_formats(info_dict['formats'])
1964 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1965 smil = self._parse_smil(doc, url, video_id)
1966 self._sort_formats(smil['formats'])
1968 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1969 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1970 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1971 info_dict['formats'] = self._parse_mpd_formats(
1973 mpd_base_url=full_response.geturl().rpartition('/')[0],
1975 self._sort_formats(info_dict['formats'])
1977 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1978 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1979 self._sort_formats(info_dict['formats'])
1981 except compat_xml_parse_error:
1984 # Is it a Camtasia project?
1985 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1986 if camtasia_res is not None:
1989 # Sometimes embedded video player is hidden behind percent encoding
1990 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1991 # Unescaping the whole page allows to handle those cases in a generic way
1992 webpage = compat_urllib_parse_unquote(webpage)
1994 # it's tempting to parse this further, but you would
1995 # have to take into account all the variations like
1996 # Video Title - Site Name
1997 # Site Name | Video Title
1998 # Video Title - Tagline | Site Name
1999 # and so on and so forth; it's just not practical
2000 video_title = self._og_search_title(
2001 webpage, default=None) or self._html_search_regex(
2002 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2005 # Try to detect age limit automatically
2006 age_limit = self._rta_search(webpage)
2007 # And then there are the jokers who advertise that they use RTA,
2008 # but actually don't.
2009 AGE_LIMIT_MARKERS = [
2010 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2012 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2015 # video uploader is domain name
2016 video_uploader = self._search_regex(
2017 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2019 video_description = self._og_search_description(webpage, default=None)
2020 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2022 # Look for Brightcove Legacy Studio embeds
2023 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2027 'url': smuggle_url(bc_url, {'Referer': url}),
2028 'ie_key': 'BrightcoveLegacy'
2029 } for bc_url in bc_urls]
2032 '_type': 'playlist',
2033 'title': video_title,
2038 # Look for Brightcove New Studio embeds
2039 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2041 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2043 # Look for ThePlatform embeds
2044 tp_urls = ThePlatformIE._extract_urls(webpage)
2046 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2048 # Look for Vessel embeds
2049 vessel_urls = VesselIE._extract_urls(webpage)
2051 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2053 # Look for embedded rtl.nl player
2054 matches = re.findall(
2055 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2058 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2060 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2062 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2064 vid_me_embed_url = self._search_regex(
2065 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2066 webpage, 'vid.me embed', default=None)
2067 if vid_me_embed_url is not None:
2068 return self.url_result(vid_me_embed_url, 'Vidme')
2070 # Look for embedded YouTube player
2071 matches = re.findall(r'''(?x)
2081 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2085 return self.playlist_from_matches(
2086 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
2088 # Look for lazyYT YouTube embed
2089 matches = re.findall(
2090 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
2092 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
2094 # Look for Wordpress "YouTube Video Importer" plugin
2095 matches = re.findall(r'''(?x)<div[^>]+
2096 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2097 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2099 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
2101 matches = DailymotionIE._extract_urls(webpage)
2103 return self.playlist_from_matches(matches, video_id, video_title)
2105 # Look for embedded Dailymotion playlist player (#3822)
2107 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2109 playlists = re.findall(
2110 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2112 return self.playlist_from_matches(
2113 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2115 # Look for embedded Wistia player
2116 wistia_url = WistiaIE._extract_url(webpage)
2119 '_type': 'url_transparent',
2120 'url': self._proto_relative_url(wistia_url),
2121 'ie_key': WistiaIE.ie_key(),
2122 'uploader': video_uploader,
2125 # Look for SVT player
2126 svt_url = SVTIE._extract_url(webpage)
2128 return self.url_result(svt_url, 'SVT')
2130 # Look for Bandcamp pages with custom domain
2131 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2132 if mobj is not None:
2133 burl = unescapeHTML(mobj.group(1))
2134 # Don't set the extractor because it can be a track url or an album
2135 return self.url_result(burl)
2137 # Look for embedded Vevo player
2139 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2140 if mobj is not None:
2141 return self.url_result(mobj.group('url'))
2143 # Look for embedded Viddler player
2145 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2147 if mobj is not None:
2148 return self.url_result(mobj.group('url'))
2150 # Look for NYTimes player
2152 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2154 if mobj is not None:
2155 return self.url_result(mobj.group('url'))
2157 # Look for Libsyn player
2159 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2160 if mobj is not None:
2161 return self.url_result(mobj.group('url'))
2163 # Look for Ooyala videos
2164 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2165 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2166 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2167 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2168 if mobj is not None:
2169 embed_token = self._search_regex(
2170 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2171 webpage, 'ooyala embed token', default=None)
2172 return OoyalaIE._build_url_result(smuggle_url(
2175 'embed_token': embed_token,
2178 # Look for multiple Ooyala embeds on SBN network websites
2179 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2180 if mobj is not None:
2181 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2183 return self.playlist_from_matches(
2184 embeds, video_id, video_title,
2185 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2187 # Look for Aparat videos
2188 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2189 if mobj is not None:
2190 return self.url_result(mobj.group(1), 'Aparat')
2192 # Look for MPORA videos
2193 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2194 if mobj is not None:
2195 return self.url_result(mobj.group(1), 'Mpora')
2197 # Look for embedded NovaMov-based player
2199 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2200 (?P<url>http://(?:(?:embed|www)\.)?
2202 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2203 videoweed\.(?:es|com)|
2204 movshare\.(?:net|sx|ag)|
2205 divxstage\.(?:eu|net|ch|co|at|ag))
2206 /embed\.php.+?)\1''', webpage)
2207 if mobj is not None:
2208 return self.url_result(mobj.group('url'))
2210 # Look for embedded Facebook player
2211 facebook_url = FacebookIE._extract_url(webpage)
2212 if facebook_url is not None:
2213 return self.url_result(facebook_url, 'Facebook')
2215 # Look for embedded VK player
2216 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2217 if mobj is not None:
2218 return self.url_result(mobj.group('url'), 'VK')
2220 # Look for embedded Odnoklassniki player
2221 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2222 if mobj is not None:
2223 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2225 # Look for embedded ivi player
2226 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2227 if mobj is not None:
2228 return self.url_result(mobj.group('url'), 'Ivi')
2230 # Look for embedded Huffington Post player
2232 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2233 if mobj is not None:
2234 return self.url_result(mobj.group('url'), 'HuffPost')
2237 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2238 if mobj is not None:
2239 return self.url_result(mobj.group('url'))
2240 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2241 if mobj is not None:
2242 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2244 # Look for funnyordie embed
2245 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2247 return self.playlist_from_matches(
2248 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2250 # Look for BBC iPlayer embed
2251 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2253 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2255 # Look for embedded RUTV player
2256 rutv_url = RUTVIE._extract_url(webpage)
2258 return self.url_result(rutv_url, 'RUTV')
2260 # Look for embedded TVC player
2261 tvc_url = TVCIE._extract_url(webpage)
2263 return self.url_result(tvc_url, 'TVC')
2265 # Look for embedded SportBox player
2266 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2268 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2270 # Look for embedded XHamster player
2271 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2273 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2275 # Look for embedded TNAFlixNetwork player
2276 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2278 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2280 # Look for embedded PornHub player
2281 pornhub_urls = PornHubIE._extract_urls(webpage)
2283 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2285 # Look for embedded DrTuber player
2286 drtuber_urls = DrTuberIE._extract_urls(webpage)
2288 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2290 # Look for embedded RedTube player
2291 redtube_urls = RedTubeIE._extract_urls(webpage)
2293 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2295 # Look for embedded Tvigle player
2297 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2298 if mobj is not None:
2299 return self.url_result(mobj.group('url'), 'Tvigle')
2301 # Look for embedded TED player
2303 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2304 if mobj is not None:
2305 return self.url_result(mobj.group('url'), 'TED')
2307 # Look for embedded Ustream videos
2308 ustream_url = UstreamIE._extract_url(webpage)
2310 return self.url_result(ustream_url, UstreamIE.ie_key())
2312 # Look for embedded arte.tv player
2314 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2316 if mobj is not None:
2317 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2319 # Look for embedded francetv player
2321 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2323 if mobj is not None:
2324 return self.url_result(mobj.group('url'))
2326 # Look for embedded smotri.com player
2327 smotri_url = SmotriIE._extract_url(webpage)
2329 return self.url_result(smotri_url, 'Smotri')
2331 # Look for embedded Myvi.ru player
2332 myvi_url = MyviIE._extract_url(webpage)
2334 return self.url_result(myvi_url)
2336 # Look for embedded soundcloud player
2337 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2339 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2341 # Look for tunein player
2342 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2344 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2346 # Look for embedded mtvservices player
2347 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2349 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2351 # Look for embedded yahoo player
2353 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2355 if mobj is not None:
2356 return self.url_result(mobj.group('url'), 'Yahoo')
2358 # Look for embedded sbs.com.au player
2362 <meta\s+property="og:video"\s+content=|
2365 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2367 if mobj is not None:
2368 return self.url_result(mobj.group('url'), 'SBS')
2370 # Look for embedded Cinchcast player
2372 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2374 if mobj is not None:
2375 return self.url_result(mobj.group('url'), 'Cinchcast')
2378 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2382 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2384 if mobj is not None:
2385 return self.url_result(mobj.group('url'), 'MLB')
2388 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2390 if mobj is not None:
2391 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2394 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2396 if mobj is not None:
2397 return self.url_result(mobj.group('url'), 'Livestream')
2399 # Look for Zapiks embed
2401 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2402 if mobj is not None:
2403 return self.url_result(mobj.group('url'), 'Zapiks')
2405 # Look for Kaltura embeds
2406 kaltura_url = KalturaIE._extract_url(webpage)
2408 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2410 # Look for Eagle.Platform embeds
2411 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2412 if eagleplatform_url:
2413 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2415 # Look for ClipYou (uses Eagle.Platform) embeds
2417 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2418 if mobj is not None:
2419 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2421 # Look for Pladform embeds
2422 pladform_url = PladformIE._extract_url(webpage)
2424 return self.url_result(pladform_url)
2426 # Look for Videomore embeds
2427 videomore_url = VideomoreIE._extract_url(webpage)
2429 return self.url_result(videomore_url)
2431 # Look for Webcaster embeds
2432 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2434 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2436 # Look for Playwire embeds
2438 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2439 if mobj is not None:
2440 return self.url_result(mobj.group('url'))
2442 # Look for 5min embeds
2444 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2445 if mobj is not None:
2446 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2448 # Look for Crooks and Liars embeds
2450 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2451 if mobj is not None:
2452 return self.url_result(mobj.group('url'))
2454 # Look for NBC Sports VPlayer embeds
2455 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2457 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2459 # Look for NBC News embeds
2460 nbc_news_embed_url = re.search(
2461 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2462 if nbc_news_embed_url:
2463 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2465 # Look for Google Drive embeds
2466 google_drive_url = GoogleDriveIE._extract_url(webpage)
2467 if google_drive_url:
2468 return self.url_result(google_drive_url, 'GoogleDrive')
2470 # Look for UDN embeds
2472 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2473 if mobj is not None:
2474 return self.url_result(
2475 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2477 # Look for Senate ISVP iframe
2478 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2480 return self.url_result(senate_isvp_url, 'SenateISVP')
2482 # Look for Dailymotion Cloud videos
2483 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2485 return self.url_result(dmcloud_url, 'DailymotionCloud')
2487 # Look for OnionStudios embeds
2488 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2489 if onionstudios_url:
2490 return self.url_result(onionstudios_url)
2492 # Look for ViewLift embeds
2493 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2495 return self.url_result(viewlift_url)
2497 # Look for JWPlatform embeds
2498 jwplatform_url = JWPlatformIE._extract_url(webpage)
2500 return self.url_result(jwplatform_url, 'JWPlatform')
2502 # Look for Digiteka embeds
2503 digiteka_url = DigitekaIE._extract_url(webpage)
2505 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2507 # Look for Arkena embeds
2508 arkena_url = ArkenaIE._extract_url(webpage)
2510 return self.url_result(arkena_url, ArkenaIE.ie_key())
2512 # Look for Piksel embeds
2513 piksel_url = PikselIE._extract_url(webpage)
2515 return self.url_result(piksel_url, PikselIE.ie_key())
2517 # Look for Limelight embeds
2518 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2520 return self.playlist_result(
2521 limelight_urls, video_id, video_title, video_description)
2523 # Look for Anvato embeds
2524 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2526 return self.playlist_result(
2527 anvato_urls, video_id, video_title, video_description)
2529 # Look for AdobeTVVideo embeds
2531 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2533 if mobj is not None:
2534 return self.url_result(
2535 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2538 # Look for Vine embeds
2540 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2542 if mobj is not None:
2543 return self.url_result(
2544 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2546 # Look for VODPlatform embeds
2548 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2550 if mobj is not None:
2551 return self.url_result(
2552 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2554 # Look for Mangomolo embeds
2556 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2558 video\?.*?\bid=(?P<video_id>\d+)|
2559 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2560 ).+?)\1''', webpage)
2561 if mobj is not None:
2563 '_type': 'url_transparent',
2564 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2565 'title': video_title,
2566 'description': video_description,
2567 'thumbnail': video_thumbnail,
2568 'uploader': video_uploader,
2570 video_id = mobj.group('video_id')
2573 'ie_key': 'MangomoloVideo',
2578 'ie_key': 'MangomoloLive',
2579 'id': mobj.group('channel_id'),
2583 # Look for Instagram embeds
2584 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2585 if instagram_embed_url is not None:
2586 return self.url_result(
2587 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2589 # Look for LiveLeak embeds
2590 liveleak_url = LiveLeakIE._extract_url(webpage)
2592 return self.url_result(liveleak_url, 'LiveLeak')
2594 # Look for 3Q SDN embeds
2595 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2598 '_type': 'url_transparent',
2599 'ie_key': ThreeQSDNIE.ie_key(),
2600 'url': self._proto_relative_url(threeqsdn_url),
2601 'title': video_title,
2602 'description': video_description,
2603 'thumbnail': video_thumbnail,
2604 'uploader': video_uploader,
2607 # Look for VBOX7 embeds
2608 vbox7_url = Vbox7IE._extract_url(webpage)
2610 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2612 # Look for DBTV embeds
2613 dbtv_urls = DBTVIE._extract_urls(webpage)
2615 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2617 # Look for Videa embeds
2618 videa_urls = VideaIE._extract_urls(webpage)
2620 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2622 # Look for 20 minuten embeds
2623 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2625 return self.playlist_from_matches(
2626 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2628 # Look for Openload embeds
2629 openload_urls = OpenloadIE._extract_urls(webpage)
2631 return self.playlist_from_matches(
2632 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2634 # Look for VideoPress embeds
2635 videopress_urls = VideoPressIE._extract_urls(webpage)
2637 return self.playlist_from_matches(
2638 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2640 # Look for Rutube embeds
2641 rutube_urls = RutubeIE._extract_urls(webpage)
2643 return self.playlist_from_matches(
2644 rutube_urls, ie=RutubeIE.ie_key())
2646 # Look for WashingtonPost embeds
2647 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2649 return self.playlist_from_matches(
2650 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2652 # Look for Mediaset embeds
2653 mediaset_urls = MediasetIE._extract_urls(webpage)
2655 return self.playlist_from_matches(
2656 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2658 # Looking for http://schema.org/VideoObject
2659 json_ld = self._search_json_ld(
2660 webpage, video_id, default={}, expected_type='VideoObject')
2661 if json_ld.get('url'):
2663 'title': video_title or info_dict['title'],
2664 'description': video_description,
2665 'thumbnail': video_thumbnail,
2666 'age_limit': age_limit
2668 info_dict.update(json_ld)
2671 # Look for HTML5 media
2672 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2674 for entry in entries:
2677 'title': video_title,
2679 self._sort_formats(entry['formats'])
2680 return self.playlist_result(entries)
2682 jwplayer_data = self._find_jwplayer_data(
2683 webpage, video_id, transform_source=js_to_json)
2685 info = self._parse_jwplayer_data(
2686 jwplayer_data, video_id, require_title=False, base_url=url)
2687 if not info.get('title'):
2688 info['title'] = video_title
2691 def check_video(vurl):
2692 if YoutubeIE.suitable(vurl):
2694 if RtmpIE.suitable(vurl):
2696 vpath = compat_urlparse.urlparse(vurl).path
2697 vext = determine_ext(vpath)
2698 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2700 def filter_video(urls):
2701 return list(filter(check_video, urls))
2703 # Start with something easy: JW Player in SWFObject
2704 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2706 # Look for gorilla-vid style embedding
2707 found = filter_video(re.findall(r'''(?sx)
2711 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2714 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2716 # Broaden the search a little bit
2717 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2719 # Broaden the findall a little bit: JWPlayer JS loader
2720 found = filter_video(re.findall(
2721 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2724 found = filter_video(re.findall(r'''(?xs)
2725 flowplayer\("[^"]+",\s*
2727 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2728 ["']?url["']?\s*:\s*["']([^"']+)["']
2733 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2735 # Try to find twitter cards info
2736 # twitter:player:stream should be checked before twitter:player since
2737 # it is expected to contain a raw stream (see
2738 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2739 found = filter_video(re.findall(
2740 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2742 # We look for Open Graph info:
2743 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2744 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2745 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2746 if m_video_type is not None:
2747 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2749 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2751 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2752 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2755 # Look also in Refresh HTTP header
2756 refresh_header = head_response.headers.get('Refresh')
2758 # In python 2 response HTTP headers are bytestrings
2759 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2760 refresh_header = refresh_header.decode('iso-8859-1')
2761 found = re.search(REDIRECT_REGEX, refresh_header)
2763 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2765 self.report_following_redirect(new_url)
2774 # twitter:player is a https URL to iframe player that may or may not
2775 # be supported by youtube-dl thus this is checked the very last (see
2776 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2777 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2779 return self.url_result(embed_url)
2782 raise UnsupportedError(url)
2785 for video_url in orderedSet(found):
2786 video_url = unescapeHTML(video_url)
2787 video_url = video_url.replace('\\/', '/')
2788 video_url = compat_urlparse.urljoin(url, video_url)
2789 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2791 # Sometimes, jwplayer extraction will result in a YouTube URL
2792 if YoutubeIE.suitable(video_url):
2793 entries.append(self.url_result(video_url, 'Youtube'))
2796 # here's a fun little line of code for you:
2797 video_id = os.path.splitext(video_id)[0]
2801 'uploader': video_uploader,
2802 'title': video_title,
2803 'age_limit': age_limit,
2806 if RtmpIE.suitable(video_url):
2807 entry_info_dict.update({
2808 '_type': 'url_transparent',
2809 'ie_key': RtmpIE.ie_key(),
2812 entries.append(entry_info_dict)
2815 ext = determine_ext(video_url)
2817 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2819 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2821 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2823 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2825 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2826 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2827 # Just matching .ism/manifest is not enough to be reliably sure
2828 # whether it's actually an ISM manifest or some other streaming
2829 # manifest since there are various streaming URL formats
2830 # possible (see [1]) as well as some other shenanigans like
2831 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2833 # Thus the most reasonable way to solve this is to delegate
2834 # to generic extractor in order to look into the contents of
2835 # the manifest itself.
2836 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2837 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2838 entry_info_dict = self.url_result(
2839 smuggle_url(video_url, {'to_generic': True}),
2842 entry_info_dict['url'] = video_url
2844 if entry_info_dict.get('formats'):
2845 self._sort_formats(entry_info_dict['formats'])
2847 entries.append(entry_info_dict)
2849 if len(entries) == 1:
2852 for num, e in enumerate(entries, start=1):
2853 # 'url' results don't have a title
2854 if e.get('title') is not None:
2855 e['title'] = '%s (%d)' % (e['title'], num)
2857 '_type': 'playlist',